Instructions to use DFloat11/FLUX.1-Kontext-dev-DF11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DFloat11/FLUX.1-Kontext-dev-DF11 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DFloat11/FLUX.1-Kontext-dev-DF11", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
HOW TO RUN THIS IN COMFYUI
Thank you so much for quantization, but how to run such fragments in comfyui.
could you please share single file if possible
If you are still interested, there is now a custom node to run Flux-dev based DF11 models: https://github.com/LeanModels/ComfyUI-DFloat11. However, many existing Flux-based DF11 models will not work because they were made for the diffusers library, and so they need to be remade specifically for ComfyUI. You can also check out my fork of the node, which has wider model support (namely Chroma), here: https://github.com/mingyi456/ComfyUI-DFloat11-Extended
I have just uploaded a ComfyUI-native Flux Kontext DF11 model here: https://huggingface.co/mingyi456/FLUX.1-Kontext-dev-DF11-ComfyUI